Graph-based semi-supervised learning plays an important role in large scale image classification tasks. However, the problem becomes very challenging in the presence of noisy labels and outliers. Moreover, traditional robust semi-supervised learning solutions suffers from prohibitive computational burdens thus cannot be computed for streaming data. Motivated by that, we present a novel unified framework robust structure-aware semi-supervised learning called Unified RSSL (URSSL) for batch processing and recursive processing robust to both outliers and noisy labels. Particularly, URSSL applies joint semi-supervised dimensionality reduction with robust estimators and network sparse regularization simultaneously on the graph Laplacian matrix iteratively to preserve the intrinsic graph structure and ensure robustness to the compound noise. First, in order to relieve the influence from outliers, a novel semi-supervised robust dimensionality reduction is applied relying on robust estimators to suppress outliers. Meanwhile, to tackle noisy labels, the denoised graph similarity information is encoded into the network regularization. Moreover, by identifying strong relevance of dimensionality reduction and network regularization in the context of robust semi-supervised learning (RSSL), a two-step alternative optimization is derived to compute optimal solutions with guaranteed convergence. We further derive our framework to adapt to large scale semi-supervised learning particularly suitable for large scale image classification and demonstrate the model robustness under different adversarial attacks. For recursive processing, we rely on reparameterization to transform the formulation to unlock the challenging problem of robust streaming-based semi-supervised learning. Last but not least, we extend our solution into distributed solutions to resolve the challenging issue of distributed robust semi-supervised learning when images are captured by multiple cameras at different locations. Extensive experimental results demonstrate the promising performance of this framework when applied to multiple benchmark datasets with respect to state-of-the-art approaches for important applications in the areas of image classification and spam data analysis.

Semisupervised learning has been widely applied to deep generative model such as variational autoencoder. However, there are still limited work in noise-robust semisupervised deep generative model where the noise exists in both of the data and the labels simultaneously, which are referred to as outliers and noisy labels or compound noise. In this article, we propose a novel noise-robust semisupervised deep generative model by jointly tackling the noisy labels and outliers in a unified robust semisupervised variational autoencoder randomized generative adversarial network (URSVAE-GAN). Typically, we consider the uncertainty of the information of the input data in order to enhance the robustness of the variational encoder toward the noisy data in our unified robust semisupervised variational autoencoder (URSVAE). Subsequently, in order to alleviate the detrimental effects of noisy labels, a denoising layer is integrated naturally into the semisupervised variational autoencoder so that the variational inference is conditioned on the corrected labels. Moreover, to enhance the robustness of the variational inference in the presence of outliers, the robust β -divergence measure is employed to derive the novel variational lower bound, which already achieves competitive performance. This further motivates the development of URSVAE-GAN that collapses the decoder of URSVAE and the generator of a robust semisupervised generative adversarial network into one unit. By applying the end-to-end denoising scheme in the joint optimization, the experimental results demonstrate the superiority of the proposed framework by the evaluating on image classification and face recognition tasks and comparing with the state-of-the-art approaches.

We present a novel unified framework robust structure-aware semi-supervised learning called Unified RSSL (URSSL) which is robust to both outliers and noisy labels where the ground truth of the corrupted labels can be either within or out of training sets. Particularly, URSSL applies joint semi-supervised dimensionality reduction with robust estimators and network sparse regularization simultaneously on the graph Laplacian matrix iteratively to preserve the intrinsic graph structure and ensure robustness to the compound noise. First, in order to relieve the influence from outliers, a novel semi-supervised robust dimensionality reduction is applied relying on robust estimators to suppress outliers. Meanwhile, to tackle noisy labels, the denoised graph similarity information is encoded into the network regularization. Moreover, by identifying strong relevance of dimensionality reduction and network regularization in the context of robust semi-supervised learning (RSSL), a two-step alternative optimization is derived to compute optimal solutions with guaranteed convergence. Extensive experimental results demonstrate the promising performance of this framework when applied to multiple benchmark datasets with respect to state-of-the-art approaches for important applications in the areas of image classification.

We propose a novel unified frameork for automated distributed active learning (AutoDAL) to address multiple challenging problems in active learning such as limited labeled data, imbalanced datasets, automatic hyperparameter selection as well as scalability to big data. First, automated graph-based semi-supervised learning is conducted by aggregating the proposed cost functions from different compute nodes and jointly optimizing hyperparameters in both the classification and query selection stages. For dense datasets, clustering-based uncertainty sampling with maximum entropy (CME) loss is applied in the optimization. For sparse and imbalanced datasets, shrinkage optimized KL-divergence regularization and local selection based active learning (SOAR) loss are further naturally adapted in AutoDAL. The optimization is efficiently resolved by iteratively executing a genetic algorithm (GA) refined with a local generating set search (GSS) and solving an integer linear programming (ILP) problem. Moreover, we propose an efficient distributed active learning algorithm which is scalable for big data. The proposed AutoDAL algorithm is applied to multiple benchmark datasets and two real-world datasets including an electrocardiogram (ECG) dataset and a credit fraud detection dataset for classification. We demonstrate that the proposed AutoDAL algorithm is capable of achieving significantly better performance compared to several state-of-the-art AutoML approaches and active learning algorithms.